NVIDIA / NVIDIA/TensorRT

How does TensorRT leverage attention masks to speed up inference ?

Open
#4,410 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

Hello team,

Thanks for all the great work,

I am training a model where I am providing tile-wise constant attention masks (see picture below).
At inference time, how will TensorRT leverage this type of attention mask to speed up inference ?

Image

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no file, test, or entry point to inspect. Start by identifying the TensorRT attention-mask and inference documentation or implementation area relevant to tile-wise constant masks. Done means establishing, with maintainer guidance, whether this mask pattern is leveraged for inference speedup and documenting the supported behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Documentation
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.